Learning Purposeful Behaviour in the Absence of Rewards

Abstract

Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a notion of progress. However, some domains have no such reward signal, or have a reward signal so sparse as to appear absent. Without reward feedback, agent behaviour is typically random, often dithering aimlessly and lacking intentionality. In this paper we present an algorithm capable of learning purposeful behaviour in the absence of rewards. The algorithm proceeds by constructing temporally extended actions (options), through the identification of purposes that are "just out of reach" of the agent's current behaviour. These purposes establish intrinsic goals for the agent to learn, ultimately resulting in a suite of behaviours that encourage the agent to visit different parts of the state space. Moreover, the approach is particularly suited for settings where rewards are very sparse, and such behaviours can help in the exploration of the environment until reward is observed.

Extended version of the paper presented at the workshop entitled Abstraction in Reinforcement Learning, at the 33rd International Conference on Machine Learning, New York, NY, USA, 2016

References in corpus (1)

• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation

Cited by in corpus (10)

• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• Hybrid Reward Architecture for Reinforcement Learning
• Deep Successor Reinforcement Learning
• A Laplacian Framework for Option Discovery in Reinforcement Learning
• A Framework for Searching for General Artificial Intelligence
• Discovering Options for Exploration by Minimizing Cover Time
• Separation of Concerns in Reinforcement Learning
• Discovery of Options via Meta-Learned Subgoals
• Temporal Abstraction in Reinforcement Learning with the Successor Representation
• Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks